@rallycry/conveyor-agent 11.0.12 → 11.0.14

package/dist/{chunk-ZNRF5EFU.js → chunk-LZWCJHVN.js}

@@ -6956,8 +6956,20 @@ var CodexTuiAdapter = class {
       cli_auth_credentials_store: "file",
       sqlite_home: codexSqliteHome(this.env),
       approval_policy: "never",
-      sandbox_mode: input.options.permissionMode === "plan" ? "read-only" : "danger-full-access",
-      developer_instructions: input.options.appendSystemPrompt ?? "",
+      // Always full access, plan mode included. Codex's own read-only mode is
+      // bubblewrap on Linux, which needs user namespaces the GKE pod spec
+      // forbids (seccomp RuntimeDefault, no unprivileged userns): every shell
+      // command died with "bwrap: No permissions to create a new namespace"
+      // before it started. A non-full-access sandbox under approval_policy
+      // "never" also rejects every mutating MCP call ("MCP tool call requires
+      // approval"), so the agent could not even report the blocker. Plan
+      // sessions stay read-only the way Claude and OpenCode plan sessions do:
+      // reader GitHub token, mode prompt, disposable pod.
+      sandbox_mode: "danger-full-access",
+      developer_instructions: [
+        input.options.appendSystemPrompt,
+        "Conveyor workflow skills are stored in .claude/skills in the workspace. When instructed to run a /skill-name skill, read .claude/skills/skill-name/SKILL.md and follow its instructions. This is a file-based workflow, not a native slash command."
+      ].filter(Boolean).join("\n\n"),
       mcp_servers: codexMcpConfig(input.mcpEntries ?? {}),
       projects: { [trustedCwd]: { trust_level: "trusted" } }
     };
@@ -14009,7 +14021,7 @@ function sessionFileExists(sessionUuid, cwd) {
 }
 function hasExistingSessionFile(taskId, cwd, lineage) {
   const key = sessionLineageKey(taskId, lineage.agentMode, lineage.runnerMode);
-  if (process.env.CONVEYOR_TUI === "codex" && lineage.runnerMode !== "code-review") {
+  if (process.env.CONVEYOR_TUI === "codex") {
     return !!readCodexLineage(taskIdToSessionUuid(key), cwd);
   }
   return sessionFileExists(taskIdToSessionUuid(key), cwd);
@@ -14329,7 +14341,7 @@ async function runSdkQuery(host, context, followUpContent, promptDeliveryOverrid
   const sessionStart = resolveSessionStart(
     sessionLineageKey(context.taskId, mode, host.config.mode),
     host.config.workspaceDir,
-    host.config.mode === "code-review" ? "claude-code" : process.env.CONVEYOR_TUI
+    host.config.mode === "code-review" && process.env.CONVEYOR_TUI !== "codex" ? "claude-code" : process.env.CONVEYOR_TUI
   );
   const hasExistingSession = !!sessionStart.resume;
   const promptDelivery = promptDeliveryOverride ?? resolvePromptDelivery({
@@ -14751,7 +14763,7 @@ function resolveHarnessKind() {
   return "pty";
 }
 function resolveCardTui(mode) {
-  if (mode === "code-review") return "claude-code";
+  if (mode === "code-review" && process.env.CONVEYOR_TUI !== "codex") return "claude-code";
   return resolveTuiKindFromEnv(process.env);
 }
 function buildPtyBridge(connection, onBackgroundTaskDone) {

package/dist/cli.js

@@ -27,7 +27,7 @@ import {
   resolveTuiKindFromEnv,
   runUsageProbe,
   sampleKeyUsage
-} from "./chunk-ZNRF5EFU.js";
+} from "./chunk-LZWCJHVN.js";
 import "./chunk-SR66HQKB.js";
 import {
   inheritedEnv,
@@ -615,7 +615,7 @@ function buildReviewChildEnv(baseEnv, data) {
   delete env.CONVEYOR_GIT_READY_MARKER;
   delete env.CONVEYOR_AGENT_MODE;
   delete env.CONVEYOR_IS_AUTO;
-  delete env.CONVEYOR_TUI;
+  if (env.CONVEYOR_TUI !== "codex") delete env.CONVEYOR_TUI;
   return env;
 }
 var ReviewChildSupervisor = class {

package/dist/index.js

@@ -1,7 +1,7 @@
 import {
   SessionRunner,
   unshallowRepo
-} from "./chunk-ZNRF5EFU.js";
+} from "./chunk-LZWCJHVN.js";
 import "./chunk-SR66HQKB.js";
 import "./chunk-JG3VMWRQ.js";
 import {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@rallycry/conveyor-agent",
-  "version": "11.0.12",
+  "version": "11.0.14",
   "description": "Conveyor Agent Runner v10 - PTY harness for the task chat (SDK harness for audit/project-chat). Agent-as-User architecture with BaseService patterns. Works locally too.",
   "keywords": [
     "agent",